Text mining-based financial expiry short message intelligent judgment method

A technology of text mining and discriminant methods, applied in finance, natural language data processing, special data processing applications, etc., can solve problems such as poor discrimination accuracy, and achieve the effect of improving accuracy, high accuracy and engineering practical value

Active Publication Date: 2017-03-29
BEIJING EMAY SOFTCOM TECH
View PDF6 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention is oriented to the financial overdue discrimination problem of short message text, and the existing supervised text classification and discrimination method has the problem of poor discrimination accuracy based on topic model, and provides an intelligent discrimination method for financial overdue short messages based on text mining

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Text mining-based financial expiry short message intelligent judgment method
  • Text mining-based financial expiry short message intelligent judgment method
  • Text mining-based financial expiry short message intelligent judgment method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] The short messages processed in the method of the present invention come from financial institutions such as banks, leasing and lending institutions, schools or associations, and various mobile app platforms to push to their users. Most of the text messages are based on certain templates, and the discrimination accuracy based on topic models is poor In order to improve the accuracy of model discrimination, a supervised overdue SMS intelligent discrimination model is proposed, considering that the word segmentation of SMS text extraction cannot be regarded as independent of each other. A method for quickly constructing a keyword dictionary; considering the heavy and continuous sample labeling work, a template-based method for quickly sampling training samples is proposed. The invention can intelligently distinguish fina...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a text mining-based financial expiry short message intelligent judgment method and belongs to the field of text data mining. The method mainly comprises the steps of obtaining short message texts, performing word segmentation, calculating the similarity of the short message texts, and extracting short message templates; sampling and tagging whether the short message templates are financial expiry short messages or not; performing word segmentation on all the short message templates, mining new words and field word groups, and forming a new word library; performing word segmentation on the short message templates again by using the new word library, extracting segmented words with important values for expiry judgment, and forming eigenvector spaces; and taking the tagged short message templates as training data, training a financial expiry classifier model by adopting a support vector machine algorithm, inputting all short messages after training, and performing expiry classification judgment. By adopting the method, the financial expiry related short messages can be quickly extracted from a large amount of short message texts, so that important reference values are provided for personal credit investigation businesses.

Description

technical field [0001] The invention belongs to the field of text data mining, and relates to a semantic analysis technology of short message data, in particular to an intelligent discrimination method for financial overdue short messages. Background technique [0002] With the rapid development of Internet finance and the development of various bank credit businesses, more and more people with economic autonomy have participated in lending affairs, and lending has become a common economic behavior. In order to standardize the lending market, reduce the cost of credit extension, enhance credit awareness, and create an atmosphere of integrity, more and more attention has been paid to personal credit investigation. Users will receive some corresponding SMS notifications when they make loans through the Internet financial platform or have loan relationships with various banks. In the process of collecting personal credit data, such text messages become a very important source o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27G06Q40/02
CPCG06F40/284G06Q40/02
Inventor 邱峰张满才
Owner BEIJING EMAY SOFTCOM TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap